Borrowing it
Nothing to install: this file belongs to Walvez/dsh-codex-sync. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Walvez/dsh-codex-sync/main/AGENTS.mdgit clone --depth 1 https://github.com/Walvez/dsh-codex-syncWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/walvez/dsh-codex-sync/agents-md)<a href="https://agentmods.dev/instructions/walvez/dsh-codex-sync/agents-md"><img src="https://agentmods.dev/badge/instructions/walvez/dsh-codex-sync/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/walvez/dsh-codex-sync/agents-md"><img src="https://agentmods.dev/badge/instructions/walvez/dsh-codex-sync/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00666 | $0.00666 |
| Opus 5.5 | $0.00266 | $0.00266 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
dsh-codex-sync AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
AGENTS.md — dsh-codex-sync
定位
一站式双向同步插件：把 OpenAI Codex 的技能/指令/会话/MCP 配置同步进 DeepSeek Harness (dsh)，并给 Codex 安装反向 MCP 桥。npm 包 dsh-codex-sync，GitHub Walvez/dsh-codex-sync。
怎么跑
npm test # 必检门禁（host 冒烟 + client SSR + reader 单测）
node bin/dsh-codex-sync.js doctor # 运行时体检
发布流程（用户硬性规则）：本地 npm test 全绿 → 装 tarball 到 web profile 让用户实测验收 → 用户确认后才推 GitHub → 再发 npm（详见 docs/RELEASE.md）。
技术栈
- dsh bundle 插件：
dsh.bundle.patch+dsh.client（{inject, platform:"web"}），exports["./client"] - client bundle 手写 CJS：
window.__ModuleLoader__.load({id, factory})，React 用 require + createElement（无 JSX/构建） - Cordis 插件模型（inject/effect/on），node:test 单测，纯 JS 无 TS
目录与约定
lib/index.js— host 插件入口（inject: systemPrompt/commands；skills/sessionPersistence/workspaceRegistry 用 ctx.get 可选读）lib/— bridge 指令注入 / skill-provider / import-service / codex-reader / convert / dsh-writer / attach-workspaces / mcp 镜像 / state 持久化 / client.jscordis.patch.yml— bundle patch（insert 行，config 默认空）examples/web-profile.cordis.patch.yml— 生产实测挂载方式：dependencies + insert 行，不要同时列进dsh.profile.bundles（duplicate loader entry id 崩溃，2026-08 实踩）- 系统块过滤在
codex-reader.mjs（SYSTEM_BLOCK + AGENTS_MD_BLOCK），改块清单要同步 test/codex-reader.test.mjs - 已导入会话在
~/.dsh/sessions/<workspace>/codex-<uuid>/，zstd 压缩，删除后可重导（导入幂等）
当前状态
v0.6.1 已发布（npm latest + GitHub main 同步）。已实现：技能桥接、指令/配置注入、会话导入（幂等/自动挂工作区/控制块剥离）、双向 MCP（自动镜像 + codex-install 反向桥）、composer 同步设置菜单、autoImport 持久化。
下一步：opencode/pi/claude-code 会话源；市场详情页截图；发布自动化。已知取舍：client 徽章读 localStorage（settings 通道对第三方命名空间封闭，勿再走 settingsScope）。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 36 lines · 666 tokens per session scan A 3ba28a6d7fa9
dsh-codex-sync AGENTS.md is an instructions file published in the GitHub repository Walvez/dsh-codex-sync (30 stars, last pushed 1mo ago), licensed MIT. It adds 666 tokens to every session, about $0.0027 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
dsh-codex-sync AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dsh-codex-sync AGENTS.mdWalvez/dsh-codex-sync | Instructions file | 30 | 1mo ago | MIT | A | 666 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |